Computational Reconstruction of Missing Data in Biological Research

More about the book

The book explores the challenges posed by missing information in biological data, such as features, labels, and samples, which hinder data analysis. It presents innovative machine learning models designed to address these issues, including deep recurrent neural networks for feature recovery and robust learning methods for label handling. Covering topics like imbalance learning and statistical inference, the book showcases applications in single-cell characterization, genome-wide studies, and medical imaging, supported by both simulated and real biological datasets.